© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3139
    Prev
    Next
    INDEX
    Explanations

    math equations or theorems, especially ones with summations, bounds or dimension

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOCTYPE
    -0.81
    </thead>
    -0.73
     MainAxisSize
    -0.73
    numerusform
    -0.68
    
    -0.68
    )++;
    -0.68
    NOPQRST
    -0.67
     htons
    -0.66
    TestingModule
    -0.65
    Parcelize
    -0.65
    POSITIVE LOGITS
     Walkover
    0.54
     Censo
    0.50
    HasAnnotation
    0.49
    sią
    0.46
    пра
    0.46
     impre
    0.45
     mieux
    0.43
     besch
    0.42
     ab
    0.42
     statistically
    0.42
    Activations Density 31.820%

    No Known Activations